Base editor predictive algorithm and method of use

Abstract

The present disclosure provides a novel machine learning model capable of assisting those of ordinary skill in the art to conduct base editing by, inter alia, facilitating the selection of an appropriate guide RNA and base editor combination which are capable of conducting base editing at a certain level of efficiency and specificity on a given input target DNA sequence desired to be edited to produce an outcome genotype of interest. The disclosure also provides base editors (e.g., ABEs and CBEs), napDNAbps, cytidine deaminases, adenosine deaminases, nucleic acid sequences encoding base editors and components thereof, vectors, and cells. In addition, the disclosure provides methods of making biological or experimental training and/or validation data for training and/or validating the machine learning computational models, as well as, vectors, libraries, and nucleic acid sequences for use in obtaining said experimental training and/or validation data.

What is claimed is: 
     
         1 . A method of using at least one machine learning model to identify at least one guide RNA for use in a base editing system for introducing a desired change in a nucleotide sequence, the base editing system comprising a napDNAbp and a deaminase, the method comprising:
 using software executing on at least one computer hardware processor to perform:
 obtaining input data indicative of the nucleotide sequence and a set of one or more guide RNAs; 
 generating first input features from the input data; 
 applying a first machine learning model to the first input features to obtain first output data indicative, for each guide RNA in the set of guide RNAs, of a base editing efficiency, at one or multiple locations in the nucleotide sequence, of the base editing system when using the each guide RNA, 
 generating second input features from the input data; 
 applying a second machine learning model to the second input features to obtain second output data indicative, for each guide RNA in the set of guide RNAs, of bystander editing activity, at one or multiple locations in the nucleotide sequence, by the base editing system when using the each guide RNA; and 
 identifying, using the first output data and the second output data, the at least one guide RNA for use in the base editing system for introducing the desired change in the nucleotide sequence. 
   
     
     
         2 . The method of  claim 1 , wherein the set of guide RNAs includes a first guide RNA, and wherein, the input data includes first data indicative of at least a part of a nucleotide sequence associated with the first guide RNA. 
     
     
         3 . The method of  claim 2 , wherein the first data specifies a spacer or a protospacer sequence associated with the first guide RNA. 
     
     
         4 . The method of  claim 1  or any other preceding claim, wherein obtaining the input data indicative of the nucleotide sequence and the set of guide RNAs, comprises:
 obtaining, by the software and from at least one source external to the software, the input data indicative of the nucleotide sequence and the set of guide RNAs. 
 
     
     
         5 . The method of  claim 1  or any other preceding claim, wherein obtaining the data indicative of the nucleotide sequence and the set of guide RNAs, comprises:
 obtaining, by the software and from at least one source external to the software, first data indicative of the nucleotide sequence; and 
 generating, from the first data indicative of the nucleotide sequence, data indicative of the set of guide RNAs. 
 
     
     
         6 . The method of  claim 1  or any other preceding claim, wherein the first machine learning model comprises a non-linear machine learning model selected from the group consisting of a random forest model, a logistic regression model, a support vector machine model, a generalized linear model, a hierarchical Bayesian model, and neural network model. 
     
     
         7 . The method of  claim 1  or any other preceding claim, wherein the first machine learning model comprises a random forest model. 
     
     
         8 . The method of  claim 1  or any other preceding claim, wherein the set of guide RNAs includes a first guide RNA, and wherein generating the first input features comprises generating multiple features to include in the first input features, the multiple features including:
 features encoding at least some nucleotides in a protospacer sequence or spacer sequence associated with the first guide RNA; and 
 features encoding at least some nucleotides, in the nucleotide sequence, located within a threshold number of nucleotides of the protospacer sequence associated with the first guide RNA. 
 
     
     
         9 . The method of  claim 8 , wherein generating the features encoding the at least some nucleotides in the protospacer sequence comprises generating a one-hot encoding of the at least some nucleotides in the protospacer sequence. 
     
     
         10 . The method of  claim 8 , wherein the multiple features further include one or more of the following features:
 features encoding at least some dinucleotides at neighboring positions in the protospacer sequence;   features representing melting temperature of the first guide RNA;   one or more features representing a total number of G, C, A, and/or T nucleotides in the protospacer sequence;   one or more features representing a percentage of G, C, A, and/or T nucleotides in the protospacer sequence; and   a feature representing an average base editing efficiency of the base editing system.   
     
     
         11 . The method of  claim 1  or any other preceding claim, wherein the set of guide RNAs includes a first guide RNA, wherein the first output data is indicative of a fraction of sequence reads containing at least one base edit at any nucleotide in a desired window about a protospacer sequence associated with the first guide RNA, among all sequence reads. 
     
     
         12 . The method of  claim 1  or any other preceding claim, wherein the second first machine learning model comprises a non-linear machine learning model selected from the group consisting of a random forest model, a logistic regression model, a support vector machine model, a generalized linear model, a hierarchical Bayesian model, and neural network model. 
     
     
         13 . The method of  claim 12  or any other preceding claim, wherein the second machine learning model comprises a deep neural network model. 
     
     
         14 . The method of  claim 13 , wherein the neural network model comprises a conditional autoregressive neural network model. 
     
     
         15 . The method of  claim 14 , wherein the conditional autoregressive neural network model includes:
 an encoder neural network mapping input data to a latent representation; and   a decoder neural network mapping the latent representation to output data,   wherein the decoder neural network has an autoregressive structure.   
     
     
         16 . The method of  claim 15 , wherein the encoder neural network comprises a multi-layer fully connected network with residual connections. 
     
     
         17 . The method of  claim 15 , wherein the decoder neural network generates a distribution over base editing outcomes at each nucleotide while conditioning on previously-generated outcomes. 
     
     
         18 . The method of  claim 13 , wherein the neural network model includes parameters representing a position-wise bias toward producing an unedited outcome. 
     
     
         19 . The method of  claim 1  or any other preceding claim, wherein the set of guide RNAs includes a first guide RNA, and wherein generating the second input features comprises generating multiple features to include in the second input features, the multiple features including:
 features encoding at least some nucleotides in a protospacer sequence or spacer sequence associated with the first guide RNA; and 
 features encoding at least some nucleotides, in the nucleotide sequence, located within a threshold number of nucleotides of the protospacer sequence associated with the first guide RNA. 
 
     
     
         20 . The method of  claim 1  or any other preceding claim, wherein the second output data is indicative of frequencies of occurrence of base editing outcomes, each of which includes edits to nucleotides at multiple positions. 
     
     
         21 . The method of  claim 1  or any other preceding claim, wherein the second output data is indicative of a frequency distribution on combinations of base editing outcomes. 
     
     
         22 . The method of  claim 1  or any other preceding claim, wherein the set of guide RNAs includes a first guide RNA, wherein, for a specific combination of base edits, the second output data is indicative of a frequency of occurrence of the specific combination of base edits among all sequenced reads containing at least one base edit at any nucleotide in a desired window about a protospacer sequence associated with the first guide RNA. 
     
     
         23 . The method of  claim 1 , wherein the set of guide RNAs includes a first guide RNA, wherein the first output data includes a first base editing efficiency value for the first guide RNA, wherein the second output data includes a first bystander editing value for the first guide RNA, and wherein identifying the guide RNA using the first output data and the second output data, comprises multiplying the first base editing efficiency value by the first bystander editing value. 
     
     
         24 . The method of  claim 1  or any other preceding claim, wherein the first machine learning model comprises a first plurality of values for a respective first plurality of parameters, the first plurality of values used by the at least one computer hardware processor to obtain the first output data from the first input features. 
     
     
         25 . The method of  claim 24  or any other preceding claim, wherein the first plurality of parameters comprises at least one thousand parameters. 
     
     
         26 . The method of  claim 25 , wherein the first plurality of parameters comprises between one thousand and ten thousand parameters. 
     
     
         27 . The method of  claim 24  or any other preceding claim, wherein the first machine learning model comprises a random forest model comprising at least 100 decision trees, each of the at least 100 decision trees having at least a depth of D, and wherein processing the input data using the random forest model comprises performing 100*D comparisons. 
     
     
         28 . The method of  claim 27 , wherein the random forest model comprises at least 500 decision trees. 
     
     
         29 . The method of  claim 27 , wherein D is greater than or equal to five, wherein processing the input data using the random forest model comprises performing at least 2500 comparisons. 
     
     
         30 . The method of  claim 1  or any other preceding claim, wherein the second machine learning model comprises a second plurality of values for a respective second plurality of parameters, the second plurality of values used by the at least one computer hardware processor to obtain the second output data from the second input features. 
     
     
         31 . The method of  claim 30 , wherein the second plurality of parameters comprises at least ten thousand parameters. 
     
     
         32 . The method of  claim 30 , wherein the second plurality of parameters comprises between 25,000 and 100,000 parameters. 
     
     
         33 . The method of  claim 30 , wherein the second plurality of parameters comprises between 30,000 and 40,000 parameters. 
     
     
         34 . The method of  claim 1  or any other preceding claim further comprising:
 synthesizing the identified guide RNA for use in the base editing system for introducing the desired change in the nucleotide sequence. 
 
     
     
         35 . The method of  claim 1  or any other preceding claim further comprising:
 using the identified guide RNA and the base editing system to introduce the desired change in a cell. 
 
     
     
         36 . The method of  claim 1  or any other preceding claim further comprising:
 determining a likelihood of whether the identified guide RNA and the base editing system, when used in combination, will result in introducing the desired change in a cell. 
 
     
     
         37 . A method for training the first machine learning model of any of  claims 1 - 36 , comprising: (i) preparing a library comprising a plurality of nucleic acid molecules each encoding a nucleotide desired sequence and a cognate guide RNA; (ii) introducing the library into a plurality of host cells; (iii) contacting the library in the host cells with a Cas-based genome editing system to produce a plurality of genomic repair products; (iv) determining the sequences of the genomic repair products; and (v) training the first machine learning model with training data that comprises at least the sequences of the genomic repair products and the cognate guide RNA. 
     
     
         38 . A method for training the second machine learning model of any of  claims 1 - 36 , comprising: (i) preparing a library comprising a plurality of nucleic acid molecules each encoding a nucleotide desired sequence and a cognate guide RNA; (ii) introducing the library into a plurality of host cells; (iii) contacting the library in the host cells with a Cas-based genome editing system to produce a plurality of genomic repair products; (iv) determining the sequences of the genomic repair products; and (v) training the second machine learning model with training data that comprises at least the sequences of the genomic repair products and the cognate guide RNA. 
     
     
         39 . At least one computer readable storage medium storing processor executable instructions that, when executed by at least one computer hardware processor, cause the at least one computer hardware processor to perform a method of using at least one machine learning model to identify at least one guide RNA for use in a base editing system for introducing a desired change in a nucleotide sequence, the base editing system comprising a napDNAbp and a deaminase, the method comprising:
 obtaining input data indicative of the nucleotide sequence and a set of one or more guide RNAs;   generating first input features from the input data;   applying a first machine learning model to the first input features to obtain first output data indicative, for each guide RNA in the set of guide RNAs, of a base editing efficiency, at one or multiple locations in the nucleotide sequence, of the base editing system when using the each guide RNA;   generating second input features from the input data;   applying a second machine learning model to the second input features to obtain second output data indicative, for each guide RNA in the set of guide RNAs, of bystander editing activity, at one or multiple locations in the nucleotide sequence, by the base editing system when using the each guide RNA; and   identifying, using the first output data and the second output data, the at least one guide RNA for use in the base editing system for introducing the desired change in the nucleotide sequence.   
     
     
         40 . A system comprising:
 at least one computer hardware processor; and   at least one computer readable storage medium storing processor executable instructions that, when executed by the at least one computer hardware processor, cause the at least one computer hardware processor to perform a method of using at least one machine learning model to identify at least one guide RNA for use in a base editing system for introducing a desired change in a nucleotide sequence, the base editing system comprising a napDNAbp and a deaminase, the method comprising:
 obtaining input data indicative of the nucleotide sequence and a set of one or more guide RNAs; 
 generating first input features from the input data; 
 applying a first machine learning model to the first input features to obtain first output data indicative, for each guide RNA in the set of guide RNAs, of a base editing efficiency, at one or multiple locations in the nucleotide sequence, of the base editing system when using the each guide RNA; 
 generating second input features from the input data; 
 applying a second machine learning model to the second input features to obtain second output data indicative, for each guide RNA in the set of guide RNAs, of bystander editing activity, at one or multiple locations in the nucleotide sequence, by the base editing system when using the each guide RNA; and 
 identifying, using the first output data and the second output data, the at least one guide RNA for use in the base editing system for introducing the desired change in the nucleotide sequence. 
   
     
     
         41 . A method of identifying at least one guide RNA for use in a base editing system for introducing a desired change in a nucleotide sequence, the base editing system comprising a napDNAbp and a deaminase, the method comprising:
 using software executing on at least one computer hardware processor to perform:
 obtaining input data indicative of the nucleotide sequence and a set of one or more guide RNAs; 
 generating first input features from the input data; 
 applying a first machine learning model to the first input features to obtain first output data indicative, for each guide RNA in the set of guide RNAs, of a base editing efficiency, at one or multiple locations in the nucleotide sequence, of the base editing system when using the each guide RNA; and 
 identifying, using the first output data, the at least one guide RNA for use in the base editing system for introducing the desired change in the nucleotide sequence. 
   
     
     
         42 . The method of  claim 41 , further comprising:
 generating second input features from the input data;   applying a second machine learning model to the second input features to obtain second output data indicative, for each guide RNA in the set of guide RNAs, of bystander editing activity, at one or multiple locations in the nucleotide sequence, by the base editing system when using the each guide RNA,   wherein identifying the guide RNA is performed using the first output data and the second output data.   
     
     
         43 . At least one computer readable storage medium storing processor executable instructions that, when executed by at least one computer hardware processor, cause the at least one computer hardware processor to perform a method of identifying at least one guide RNA for use in a base editing system for introducing a desired change in a nucleotide sequence, the base editing system comprising a napDNAbp and a deaminase, the method comprising:
 obtaining input data indicative of the nucleotide sequence and a set of one or more guide RNAs;   generating first input features from the input data;   applying a first machine learning model to the first input features to obtain first output data indicative, for each guide RNA in the set of guide RNAs, of a base editing efficiency, at one or multiple locations in the nucleotide sequence, of the base editing system when using the each guide RNA; and   identifying, using the first output data, the at least one guide RNA for use in the base editing system for introducing the desired change in the nucleotide sequence.   
     
     
         44 . A system, comprising:
 at least one computer hardware processor; and   at least one computer readable storage medium storing processor executable instructions that, when executed by the at least one computer hardware processor, cause the at least one computer hardware processor to perform a method of identifying at least one guide RNA for use in a base editing system for introducing a desired change in a nucleotide sequence, the base editing system comprising a napDNAbp and a deaminase, the method comprising:
 obtaining input data indicative of the nucleotide sequence and a set of one or more guide RNAs; 
 generating first input features from the input data; 
 applying a first machine learning model to the first input features to obtain first output data indicative, for each guide RNA in the set of guide RNAs, of a base editing efficiency, at one or multiple locations in the nucleotide sequence, of the base editing system when using the each guide RNA; and 
 identifying, using the first output data, the at least one guide RNA for use in the base editing system for introducing the desired change in the nucleotide sequence. 
   
     
     
         45 . A method of identifying at least one guide RNA for use in a base editing system for introducing a desired change in a nucleotide sequence, the base editing system comprising a napDNAbp and a deaminase, the method comprising:
 using software executing on at least one computer hardware processor to perform:
 obtaining input data indicative of the nucleotide sequence and a set of one or more guide RNAs; 
 generating first input features from the input data; 
 applying a first machine learning model to the first input features to obtain first output data indicative, for each guide RNA in the set of guide RNAs, of bystander editing activity, at one or multiple locations in the nucleotide sequence, by the base editing system when using the each guide RNA; and 
 identifying, using the first output data, the at least one guide RNA for use in the base editing system for introducing the desired change in the nucleotide sequence. 
   
     
     
         46 . The method of  claim 45 , further comprising:
 generating second input features from the input data;   applying a second machine learning model to the second input features to obtain second output data indicative, for each guide RNA in the set of guide RNAs, of a base editing efficiency, at one or multiple locations in the nucleotide sequence, of the base editing system when using the each guide RNA,   wherein identifying the guide RNA is performed using the first output data and the second output data.   
     
     
         47 . At least one computer readable storage medium storing processor executable instructions that, when executed by at least one computer hardware processor, cause the at least one computer hardware processor to perform a method of identifying at least one guide RNA for use in a base editing system for introducing a desired change in a nucleotide sequence, the base editing system comprising a napDNAbp and a deaminase, the method comprising:
 obtaining input data indicative of the nucleotide sequence and a set of one or more guide RNAs;   generating first input features from the input data;   applying a first machine learning model to the first input features to obtain first output data indicative, for each guide RNA in the set of guide RNAs, of bystander editing activity, at one or multiple locations in the nucleotide sequence, by the base editing system when using the each guide RNA; and   identifying, using the first output data, the at least one guide RNA for use in the base editing system for introducing the desired change in the nucleotide sequence.   
     
     
         48 . A system, comprising:
 at least one computer hardware processor; and   at least one computer readable storage medium storing processor executable instructions that, when executed by at least one computer hardware processor, cause the at least one computer hardware processor to perform a method of identifying at least one guide RNA for use in a base editing system for introducing a desired change in a nucleotide sequence, the base editing system comprising a napDNAbp and a deaminase, the method comprising:
 obtaining input data indicative of the nucleotide sequence and a set of one or more guide RNAs; 
 generating first input features from the input data; 
 applying a first machine learning model to the first input features to obtain first output data indicative, for each guide RNA in the set of guide RNAs, of bystander editing activity, at one or multiple locations in the nucleotide sequence, by the base editing system when using the each guide RNA; and 
 identifying, using the first output data, the at least one guide RNA for use in the base editing system for introducing the desired change in the nucleotide sequence. 
   
     
     
         49 . A method, comprising:
 using software executing on at least one computer hardware processor to perform:
 receiving input data indicative of a selection of:
 a nucleotide sequence; 
 a base editing system comprising a napDNAbp and a deaminase; and 
 a first guide RNA; 
 
 applying a first machine learning model to the first input features, generated from the input data, to obtain first output data indicative of a base editing efficiency, at a desired location in the nucleotide sequence, of the base editing system when using the first guide RNA; 
 applying a second machine learning model to the second input features, generated from the input data, to obtain second output data indicative of bystander editing activity, at one or multiple locations in the nucleotide sequence, by the base editing system when using the first guide RNA; and 
 determining, using the first output data and the second output data, a likelihood of whether the first guide RNA and the base editing system, when used in combination, will result in introduce a desired change to the nucleotide sequence in a cell. 
   
     
     
         50 . At least one computer-readable storage medium storing processor-executable instructions that, when executed by at least one computer hardware processor, cause the at least one computer processor to perform:
 receiving input data indicative of a selection of:
 a nucleotide sequence; 
 a base editing system comprising a napDNAbp and a deaminase; and 
 a first guide RNA; 
   applying a first machine learning model to the first input features, generated from the input data, to obtain first output data indicative of a base editing efficiency, at a desired location in the nucleotide sequence, of the base editing system when using the first guide RNA;   applying a second machine learning model to the second input features, generated from the input data, to obtain second output data indicative of bystander editing activity, at one or multiple locations in the nucleotide sequence, by the base editing system when using the first guide RNA; and   determining, using the first output data and the second output data, a likelihood of whether the first guide RNA and the base editing system, when used in combination, will result in introduce a desired change to the nucleotide sequence in a cell.   
     
     
         51 . A system, comprising:
 at least one computer hardware processor; and   at least one computer-readable storage medium storing processor-executable instructions that, when executed by the at least one computer hardware processor, cause the at least one computer processor to perform:
 receiving input data indicative of a selection of:
 a nucleotide sequence; 
 a base editing system comprising a napDNAbp and a deaminase; and 
 a first guide RNA; 
 
 applying a first machine learning model to the first input features, generated from the input data, to obtain first output data indicative of a base editing efficiency, at a desired location in the nucleotide sequence, of the base editing system when using the first guide RNA; 
 applying a second machine learning model to the second input features, generated from the input data, to obtain second output data indicative of bystander editing activity, at one or multiple locations in the nucleotide sequence, by the base editing system when using the first guide RNA; and 
 determining, using the first output data and the second output data, a likelihood of whether the first guide RNA and the base editing system, when used in combination, will result in introduce a desired change to the nucleotide sequence in a cell. 
   
     
     
         52 . A guide RNA for use in a base editing system for introducing a target change into a target DNA sequence identified by the method of any of  claims 1 - 51 . 
     
     
         53 . A guide RNA comprising a protospacer selected from the group consisting of SEQ ID Nos: 451-3199. 
     
     
         54 . The guide RNA of any of  claims 52 - 53 , wherein at least one base editor demonstrated at least 50% correction precision to the wild-type genotype among edited reads. 
     
     
         55 . The guide RNA of any of  claims 52 - 54 , wherein the least one base editor is ABE (SEQ ID NO: 3210), ABE-CP1041 (SEQ ID NO: 3211), AID-BE4 (SEQ ID NO: 3202), BE4 (SEQ ID NO: 3200), BE4-CP1028 (SEQ ID NO: 3208), CDA-BE4 (SEQ ID NO: 3203), eA3A-BE4 (SEQ ID NO: 3205), eA3A_T31AT44A, or evoAPOBEC1-BE4max (SEQ ID NO: 3204). 
     
     
         56 . The guide RNA of any of  claims 52 - 55 , wherein the base editing system comprises an ABE of SEQ ID NO: 3210 and said guide RNA comprises a protospacer identified as any of the sequences of Index Nos. 880-2498 of Table 5. 
     
     
         57 . The guide RNA of any of  claims 52 - 56 , wherein the base editing system comprises an ABE-CP1041 of SEQ ID NO: 3211, and said guide RNA comprises a protospacer identified as any of the sequences of Index Nos. 880-990, 998-1014, 1042-1313, 1749-2184, 2186-2695 of Table 5. 
     
     
         58 . The guide RNA of any of  claims 52 - 57 , wherein the base editing system comprises an AID-BE4 of SEQ ID NO: 3202, and said guide RNA comprises a protospacer identified as any of the sequences of Index Nos. 1-301 of Table 5. 
     
     
         59 . The guide RNA of any of  claims 52 - 58 , wherein the base editing system comprises an BE4 of SEQ ID NO: 3200, and said guide RNA comprises a protospacer identified as any of the sequences of Index Nos. 2-3, 6-12, 16-17, 19-27, 40-42, 44, 47-48, 52-53, 55-58, 62-65, 68, 70, 74-78, 80, 82-92, 94-98, 198, 200-204, 207, 210-211, 213-219, 222-224, 226-229, 231-233, 235-236, 238, 244, 247-248, 252-255, 257-258, 260, 263-270, 272-275, 279, 281-287, 289-290, 293-294, 296, 298-299, 301, 541, 543-626, 628-712, 722-723, 798-838, 840-848, 858-878 of Table 5. 
     
     
         60 . The guide RNA of any of  claims 52 - 59 , wherein the base editing system comprises an BE4-CP1028 of SEQ ID NO: 3208, and said guide RNA comprises a protospacer identified as any of the sequences of Index Nos. 2-3, 5-9, 11-15, 17-27, 40, 42, 44, 47-50, 52-54, 56-58, 63, 65, 74-75, 77, 79-83, 85, 87-93, 96-98, 157, 162, 182, 263, 302, 305, 308, 313, 315, 324, 336, 338, 341, 343, 345, 403, 407-411, 413, 415-416, 418-419, 421, 423-427, 429-440, 461-464, 467-468, 470-471, 473, 508-514, 516-520, 522-524, 526-535, 537, 539-540, 544, 586, 588-590, 592-605, 607, 621, 624, 632, 702-703, 705-708, 710-712, 723, 799-801, 803-804, 807-808, 810, 813-816, 818-828, 830-835, 837-838, 840-848, 858-860, 864-873, 876-878 of Table 5. 
     
     
         61 . The guide RNA of any of  claims 52 - 60 , wherein the base editing system comprises an CDA-BE4 of SEQ ID NO: 3203, and said guide RNA comprises a protospacer identified as any of the sequences of Index Nos. 4, 6-7, 9-13, 15-17, 20-24, 26, 31-32, 35, 40-41, 44, 47-50, 52-53, 55, 63-65, 68, 70-72, 75-81, 84-87, 89-94, 98, 100-101, 103-104, 107, 109, 111, 113, 118-121, 124-127, 130-132, 136, 141-144, 146-148, 151-160, 162, 164, 166-167, 170, 172-173, 175-180, 184, 195, 198, 200-204, 206-215, 218-219, 221-224, 226-227, 230, 233-234, 237, 239, 243-244, 247, 251-257, 261-267, 274, 281-284, 286-287, 289-290, 292, 295, 297-302, 304, 411-412, 414, 417, 420, 422-423, 425, 428, 431, 433, 435, 438, 442-445, 457, 463, 472, 477-479, 485, 488, 491, 493-494, 507, 510, 513, 515, 518, 521, 536, 538, 540, 542, 552, 561, 563-569, 573-582, 587-588, 591, 593-595, 598, 622-623, 625, 627, 640, 667, 704, 712-721, 724-727, 734-752, 755, 759, 761-768, 773-774, 776, 780, 785-786, 788-789, 795-797, 800, 802, 805-806, 811-812, 814, 817-818, 820, 829, 831, 833, 835, 839-842, 849, 852, 854, 856, 861, 864, 874-875, 878-879 of Table 5. 
     
     
         62 . The guide RNA of any of  claims 52 - 61 , wherein the base editing system comprises an eA3A-BE4 of SEQ ID NO: 3204, and said guide RNA comprises a protospacer identified as any of the sequences of Index Nos. 2-3, 6, 8-10, 13, 15-17, 20, 22-23, 25, 27-28, 32, 35, 42, 45-47, 53, 55-56, 63-64, 74, 76, 80-81, 86-92, 96-98, 111, 119, 121, 127, 151, 154, 156, 159-160, 171, 178, 180, 184, 192, 198, 204-206, 210-211, 214, 216-217, 220, 224, 228-229, 231-233, 235, 244, 247, 252-253, 260, 263-268, 270, 272-274, 276, 279, 281-285, 287-289, 293-294, 296, 298, 303-304, 306-312, 314, 316-317, 319-323, 326-329, 331-337, 339, 343-345, 347-348, 352-362, 364-372, 374-406, 410-411, 432-434, 438, 446-447, 449-453, 456, 458, 460, 466, 468-469, 474-476, 481, 486, 489-490, 492, 495-506, 521, 523, 525, 539, 543-551, 553-556, 558-564, 569, 573, 575, 578-579, 581, 583-584, 588, 590, 593, 595-596, 598-600, 602, 604, 607, 614-620, 622, 624, 626, 628-630, 632-639, 641-647, 651, 657, 660, 662-663, 665-666, 668-671, 673-674, 678, 686-689, 691-693, 695-700, 702-703, 707-709, 711-712, 715, 723, 741, 800-806, 808, 811, 813-821, 823-827, 829-830, 832-833, 835, 844, 846-849, 852, 858-860, 865-866, 868-870, 872-874, 878, 2696-2737 of Table 5. 
     
     
         63 . The guide RNA of any of  claims 52 - 62 , wherein the base editing system comprises an eA3A_T31AT44A of SEQ ID NO: 3206, and said guide RNA comprises a protospacer identified as any of the sequences of Index Nos. 2725-2726 and 2738-2749 of Table 5. 
     
     
         64 . The guide RNA of any of  claims 52 - 63 , wherein the base editing system comprises an evoAPOBEC1-BE4max of SEQ ID NO: 3204, and said guide RNA comprises a protospacer identified as any of the sequences of Index Nos. 1-4, 6-7, 9-11, 13, 15-18, 20, 22-27, 32, 35, 40-42, 44, 47-49, 51-53, 55-56, 58, 61-63, 68, 70-72, 74, 76-82, 84-92, 94-98, 100, 104, 108, 111, 116, 121, 125-126, 131, 136, 141-143, 146-148, 150-151, 153, 155-160, 162, 170, 172, 175, 178-180, 183-184, 190, 195, 198, 200-201, 203-204, 206, 210-212, 214, 217, 220-221, 223-227, 229, 231-233, 235-239, 244, 247, 249, 252-258, 263-270, 272-274, 276, 278-279, 281-284, 286-290, 293-294, 296, 298, 300-301, 304, 318, 321, 324-325, 330-333, 338, 340, 342, 346, 349-351, 358, 363, 373, 379-380, 385-389, 411, 423, 425, 427, 431, 433, 438, 441, 445, 448, 454-455, 459, 463, 465, 472, 476, 480, 482-484, 487, 491, 493-494, 503, 510, 514, 517, 521, 535, 540, 542, 544-545, 551-555, 558-564, 567-568, 573-576, 579-582, 588-589, 593, 595-596, 598, 600, 603, 605, 610, 612-617, 620, 622, 625-626, 628, 630-631, 635-641, 644, 651, 653-654, 656, 676, 678-679, 682, 688, 694, 704, 711, 713-715, 717, 720-723, 728-734, 742-743, 745, 747, 750, 752-754, 756-758, 760, 762, 766, 769-773, 775, 777-779, 781-784, 787, 790-794, 798, 800, 803, 805-806, 809, 811-812, 814, 818-819, 824-825, 827, 829, 831, 833, 835, 838-839, 841-842, 847, 850-855, 857-859, 861, 864, 870-873, 875, 878-879 of Table 5. 
     
     
         65 . A complex comprising a base editor and a guide RNA selected from the method of  claim 1  or a guide RNA of any one of  claims 52 - 64 . 
     
     
         66 . The complex of  claim 65 , wherein the base editor comprises a napDNAbp. 
     
     
         67 . The complex of  claim 66 , wherein the napDNAbp is a Cas9 or variant thereof. 
     
     
         68 . The complex of  claim 66 , wherein the napDNAbp is a wildtype SpCas9 comprising an amino acid sequence of SEQ ID NO: 5, or an amino acid sequence having at least 80%, 85%, 90%, 95%, or 99% sequence identity with SEQ ID NO: 5. 
     
     
         69 . The complex of  claim 66 , wherein the napDNAbp is a wildtype SpCas9 comprising an amino acid sequence of SEQ ID NOs: 5, 8, 10, 12, and 407 or an amino acid sequence having at least 80%, 85%, 90%, 95%, or 99% sequence identity with any one of SEQ ID NOs: 5, 8, 10, 12, or 407. 
     
     
         70 . The complex of  claim 66 , wherein the napDNAbp is a SpCas9 ortholog or homolog comprising an amino acid sequence of SEQ ID Nos: 13-26, 44-63, or 74-77, or an amino acid sequence having at least 80%, 85%, 90%, 95%, or 99% sequence identity with any one of SEQ ID NOs: 13-26, 44-63, or 74-77. 
     
     
         71 . The complex of  claim 66 , wherein the napDNAbp is a dead Cas9 comprising an amino acid sequence of SEQ ID Nos: 27-28, or an amino acid sequence having at least 80%, 85%, 90%, 95%, or 99% sequence identity with any one of SEQ ID NOs: 27-28. 
     
     
         72 . The complex of  claim 66 , wherein the napDNAbp is a nickase Cas9 comprising an amino acid sequence of SEQ ID Nos: 29-44, or an amino acid sequence having at least 80%, 85%, 90%, 95%, or 99% sequence identity with any one of SEQ ID NOs: 29-44. 
     
     
         73 . The complex of  claim 66 , wherein the napDNAbp is a circular permutant variant of Cas9 comprising an amino acid sequence of SEQ ID Nos: 64-73, or an amino acid sequence having at least 80%, 85%, 90%, 95%, or 99% sequence identity with any one of SEQ ID NOs: 64-73. 
     
     
         74 . The complex of  claim 65 , wherein the base editor comprises an adenine deaminase. 
     
     
         75 . The complex of  claim 65 , wherein the base editor comprises a cytidine deaminase. 
     
     
         76 . The complex of  claim 74 , wherein the adenine deaminase comprises an amino acid sequence of any one of SEQ ID NOs: 78-91, 403, or 462, or an amino acid sequence having at least 80%, 85%, 90%, 95%, or 99% sequence identity with any one of SEQ ID NOs: 78-91, 403, or 462. 
     
     
         77 . The complex of  claim 75 , wherein the cytidine deaminase comprises an amino acid sequence of any one of SEQ ID NOs: 92-134, or an amino acid sequence having at least 80%, 85%, 90%, 95%, or 99% sequence identity with any one of SEQ ID NOs: 92-134. 
     
     
         78 . The complex of  claim 65 , wherein the base editor comprises one or more linkers having an amino acid sequence comprising any one of SEQ ID NOs.: 135-151, or an amino acid sequence having at least 80%, 85%, 90%, 95%, or 99% sequence identity with any one of SEQ ID NOs: 135-151. 
     
     
         79 . The complex of  claim 65 , wherein the base editor comprises one or more NLS having an amino acid sequence comprising any one of SEQ ID NOs.: 152-162, or an amino acid sequence having at least 80%, 85%, 90%, 95%, or 99% sequence identity with any one of SEQ ID NOs: 152-162. 
     
     
         80 . The complex of  claim 65 , wherein the base editor comprises one or more UGI having an amino acid sequence comprising SEQ ID NO.: 163, or an amino acid sequence having at least 80%, 85%, 90%, 95%, or 99% sequence identity with SEQ ID NO:163. 
     
     
         81 . The complex of  claim 65 , wherein the base editor is an adenosine base editor comprising an amino acid sequence of any one of SEQ ID NOs: 174-221 or 463-476, or an amino acid sequence having at least 80%, 85%, 90%, 95%, or 99% sequence identity with any one of SEQ ID NOs: 174-221 or 463-476. 
     
     
         82 . The complex of  claim 65 , wherein the base editor is a cytidine base editor comprising an amino acid sequence of any one of SEQ ID NOs: 223-248, or an amino acid sequence having at least 80%, 85%, 90%, 95%, or 99% sequence identity with any one of SEQ ID NOs: 223-248. 
     
     
         83 . The complex of  claim 65 , wherein the base editor is ABE (SEQ ID NO: 3210), ABE-CP1041 (SEQ ID NO: 3211), AID-BE4 (SEQ ID NO: 3202), BE4 (SEQ ID NO: 3200), BE4-CP1028 (SEQ ID NO: 3208), CDA-BE4 (SEQ ID NO: 3203), eA3A-BE4 (SEQ ID NO: 3205), eA3A_T31AT44A (SEQ ID NO: 3206), or evoAPOBEC1-BE4max (SEQ ID NO: 3204), or an amino acid sequence having at least 80%, 85%, 90%, 95%, or 99% sequence identity with any one of SEQ ID NOs: 3210, 3211, 3202, 3200, 3208, 3203, 3205, 3206, or 3204. 
     
     
         84 . The complex of  claim 65 , wherein the guide RNA comprises a spacer corresponding to any one of the protospacers of SEQ ID Nos: 451-3199. 
     
     
         85 . The complex of  claim 65 , wherein the base editing system comprises an ABE of SEQ ID NO: 3210 and said guide RNA comprises a spacer corresponding to any one of the protospacers identified as a sequence of Index Nos. 880-2498 of Table 5. 
     
     
         86 . The complex of  claim 65 , wherein the base editing system comprises an ABE-CP1041 of SEQ ID NO: 3211, said guide RNA comprises a spacer corresponding to any one of the protospacers identified as a sequence of Index Nos. 880-990, 998-1014, 1042-1313, 1749-2184, 2186-2695 of Table 5. 
     
     
         87 . The complex of  claim 65 , wherein the base editing system comprises an AID-BE4 of SEQ ID NO: 3202, said guide RNA comprises a spacer corresponding to any one of the protospacers identified as a sequence of Index Nos. 1-301 of Table 5. 
     
     
         88 . The complex of  claim 65 , wherein the base editing system comprises an BE4 of SEQ ID NO: 3200, said guide RNA comprises a spacer corresponding to any one of the protospacers identified as a sequence of Index Nos. 2-3, 6-12, 16-17, 19-27, 40-42, 44, 47-48, 52-53, 55-58, 62-65, 68, 70, 74-78, 80, 82-92, 94-98, 198, 200-204, 207, 210-211, 213-219, 222-224, 226-229, 231-233, 235-236, 238, 244, 247-248, 252-255, 257-258, 260, 263-270, 272-275, 279, 281-287, 289-290, 293-294, 296, 298-299, 301, 541, 543-626, 628-712, 722-723, 798-838, 840-848, 858-878 of Table 5. 
     
     
         89 . The complex of  claim 65 , wherein the base editing system comprises an BE4-CP1028 of SEQ ID NO: 3208, said guide RNA comprises a spacer corresponding to any one of the protospacers identified as a sequence of Index Nos. 2-3, 5-9, 11-15, 17-27, 40, 42, 44, 47-50, 52-54, 56-58, 63, 65, 74-75, 77, 79-83, 85, 87-93, 96-98, 157, 162, 182, 263, 302, 305, 308, 313, 315, 324, 336, 338, 341, 343, 345, 403, 407-411, 413, 415-416, 418-419, 421, 423-427, 429-440, 461-464, 467-468, 470-471, 473, 508-514, 516-520, 522-524, 526-535, 537, 539-540, 544, 586, 588-590, 592-605, 607, 621, 624, 632, 702-703, 705-708, 710-712, 723, 799-801, 803-804, 807-808, 810, 813-816, 818-828, 830-835, 837-838, 840-848, 858-860, 864-873, 876-878 of Table 5. 
     
     
         90 . The complex of  claim 65 , wherein the base editing system comprises an CDA-BE4 of SEQ ID NO: 3203, said guide RNA comprises a spacer corresponding to any one of the protospacers identified as a sequence of Index Nos. 4, 6-7, 9-13, 15-17, 20-24, 26, 31-32, 35, 40-41, 44, 47-50, 52-53, 55, 63-65, 68, 70-72, 75-81, 84-87, 89-94, 98, 100-101, 103-104, 107, 109, 111, 113, 118-121, 124-127, 130-132, 136, 141-144, 146-148, 151-160, 162, 164, 166-167, 170, 172-173, 175-180, 184, 195, 198, 200-204, 206-215, 218-219, 221-224, 226-227, 230, 233-234, 237, 239, 243-244, 247, 251-257, 261-267, 274, 281-284, 286-287, 289-290, 292, 295, 297-302, 304, 411-412, 414, 417, 420, 422-423, 425, 428, 431, 433, 435, 438, 442-445, 457, 463, 472, 477-479, 485, 488, 491, 493-494, 507, 510, 513, 515, 518, 521, 536, 538, 540, 542, 552, 561, 563-569, 573-582, 587-588, 591, 593-595, 598, 622-623, 625, 627, 640, 667, 704, 712-721, 724-727, 734-752, 755, 759, 761-768, 773-774, 776, 780, 785-786, 788-789, 795-797, 800, 802, 805-806, 811-812, 814, 817-818, 820, 829, 831, 833, 835, 839-842, 849, 852, 854, 856, 861, 864, 874-875, 878-879 of Table 5. 
     
     
         91 . The complex of  claim 65 , wherein the base editing system comprises an eA3A-BE4 of SEQ ID NO: 3204, said guide RNA comprises a spacer corresponding to any one of the protospacers identified as a sequence of Index Nos. 2-3, 6, 8-10, 13, 15-17, 20, 22-23, 25, 27-28, 32, 35, 42, 45-47, 53, 55-56, 63-64, 74, 76, 80-81, 86-92, 96-98, 111, 119, 121, 127, 151, 154, 156, 159-160, 171, 178, 180, 184, 192, 198, 204-206, 210-211, 214, 216-217, 220, 224, 228-229, 231-233, 235, 244, 247, 252-253, 260, 263-268, 270, 272-274, 276, 279, 281-285, 287-289, 293-294, 296, 298, 303-304, 306-312, 314, 316-317, 319-323, 326-329, 331-337, 339, 343-345, 347-348, 352-362, 364-372, 374-406, 410-411, 432-434, 438, 446-447, 449-453, 456, 458, 460, 466, 468-469, 474-476, 481, 486, 489-490, 492, 495-506, 521, 523, 525, 539, 543-551, 553-556, 558-564, 569, 573, 575, 578-579, 581, 583-584, 588, 590, 593, 595-596, 598-600, 602, 604, 607, 614-620, 622, 624, 626, 628-630, 632-639, 641-647, 651, 657, 660, 662-663, 665-666, 668-671, 673-674, 678, 686-689, 691-693, 695-700, 702-703, 707-709, 711-712, 715, 723, 741, 800-806, 808, 811, 813-821, 823-827, 829-830, 832-833, 835, 844, 846-849, 852, 858-860, 865-866, 868-870, 872-874, 878, 2696-2737 of Table 5. 
     
     
         92 . The complex of  claim 65 , wherein the base editing system comprises an eA3A_T31AT44A of SEQ ID NO: 3206, said guide RNA comprises a spacer corresponding to any one of the protospacers identified as a sequence of Index Nos. 2725-2726 and 2738-2749 of Table 5. 
     
     
         93 . The complex of  claim 65 , wherein the base editing system comprises an evoAPOBEC1-BE4max of SEQ ID NO: 3204, said guide RNA comprises a spacer corresponding to any one of the protospacers identified as a sequence of Index Nos. 1-4, 6-7, 9-11, 13, 15-18, 20, 22-27, 32, 35, 40-42, 44, 47-49, 51-53, 55-56, 58, 61-63, 68, 70-72, 74, 76-82, 84-92, 94-98, 100, 104, 108, 111, 116, 121, 125-126, 131, 136, 141-143, 146-148, 150-151, 153, 155-160, 162, 170, 172, 175, 178-180, 183-184, 190, 195, 198, 200-201, 203-204, 206, 210-212, 214, 217, 220-221, 223-227, 229, 231-233, 235-239, 244, 247, 249, 252-258, 263-270, 272-274, 276, 278-279, 281-284, 286-290, 293-294, 296, 298, 300-301, 304, 318, 321, 324-325, 330-333, 338, 340, 342, 346, 349-351, 358, 363, 373, 379-380, 385-389, 411, 423, 425, 427, 431, 433, 438, 441, 445, 448, 454-455, 459, 463, 465, 472, 476, 480, 482-484, 487, 491, 493-494, 503, 510, 514, 517, 521, 535, 540, 542, 544-545, 551-555, 558-564, 567-568, 573-576, 579-582, 588-589, 593, 595-596, 598, 600, 603, 605, 610, 612-617, 620, 622, 625-626, 628, 630-631, 635-641, 644, 651, 653-654, 656, 676, 678-679, 682, 688, 694, 704, 711, 713-715, 717, 720-723, 728-734, 742-743, 745, 747, 750, 752-754, 756-758, 760, 762, 766, 769-773, 775, 777-779, 781-784, 787, 790-794, 798, 800, 803, 805-806, 809, 811-812, 814, 818-819, 824-825, 827, 829, 831, 833, 835, 838-839, 841-842, 847, 850-855, 857-859, 861, 864, 870-873, 875, 878-879 of Table 5. 
     
     
         94 . One or more polynucleotides encoding the complex of any of  claims 65 - 93 . 
     
     
         95 . A vector comprising the one or more polynucleotides of  claim 94  and one or more promoters that drive the expression of the base editor and the guide RNA. 
     
     
         96 . A cell comprising the vector of  claim 95 . 
     
     
         97 . A cell comprising a complex of any of  claims 65 - 93 . 
     
     
         98 . A pharmaceutical composition comprising: (i) a guide RNA selected from the method of  claim 1 , a complex of any one of  claims 65 - 93 , a polynucleotide of  claim 94 , or a vector of  claim 95 ; and (ii) a pharmaceutically acceptable excipient. 
     
     
         99 . A method of editing a target DNA sequence by base editing using a base editor:
 selecting a guide RNA for use in the base editing system in accordance with the method of any of  claims 1 - 36 ; and   contacting the genome of the target DNA sequence with the selected guide RNA and the base editor, thereby editing the target DNA sequence.   
     
     
         100 . The method of  claim 99 , wherein the method is conducted ex vivo, in vivo, or ex vivo. 
     
     
         101 . The method of  claim 1 , wherein the method restores the function of a disease-causing mutation. 
     
     
         102 . The method of  claim 99 , wherein the method of editing introduces a nucleotide change in the target DNA sequence. 
     
     
         103 . The method of  claim 102 , wherein the nucleotide change is a single nucleotide substitution, a deletion, an insertion, or a combination thereof. 
     
     
         104 . The method of  claim 102 , wherein the nucleotide change is a transition mutation. 
     
     
         105 . The method of  claim 104 , wherein the transition mutation is a G to A substitution, a T to C substitution, a C to T substitution, or an A to G substitution. 
     
     
         106 . The method of  claim 102 , wherein the nucleotide change corrects a mutation in a disease-associated gene. 
     
     
         107 . The method of  claim 106 , wherein the disease-associated gene is associated with cardiac disease; high blood pressure; neurological disease; autoimmune disorder, arthritis; diabetes; cancer; or obesity. 
     
     
         108 . The method of  claim 106 , wherein the disease-associated gene is associated with Adenosine Deaminase (ADA) Deficiency; Alpha-1 Antitrypsin Deficiency; Cystic Fibrosis; Duchenne Muscular Dystrophy; Galactosemia; Hemochromatosis; Huntington's Disease; Maple Syrup Urine Disease; Marfan Syndrome; Neurofibromatosis Type 1; Pachyonychia Congenita; Phenylkeotnuria; Severe Combined Immunodeficiency; Sickle Cell Disease; Smith-Lemli-Opitz Syndrome; and Tay-Sachs Disease, or other monogenetic disorder. 
     
     
         109 . The library of the training method of  claim 37 . 
     
     
         110 . The library of the training method of  claim 38 . 
     
     
         111 . The method of  claim 1 , wherein the first machine learning model is trained using training data generated in part using the base editing system. 
     
     
         112 . The method of  claim 49 , further comprising:
 prior to performing the applying,   selecting, based on the editing system indicated by the input data, the first machine learning model and the second machine learning model from a plurality of machine learning models.